License plate recognition using DTCNNs

被引：39

作者：

ter Brugge, MH ^{[1
]}

Stevens, JH ^{[1
]}

Nijhuis, JAG ^{[1
]}

Spaanenburg, L ^{[1
]}

机构：

[1] Univ Groningen, Dept Comp Sci, NL-9700 AV Groningen, Netherlands

来源：

CNNA 98 - 1998 FIFTH IEEE INTERNATIONAL WORKSHOP ON CELLULAR NEURAL NETWORKS AND THEIR APPLICATIONS - PROCEEDINGS | 1998年

关键词：

D O I：

10.1109/CNNA.1998.685366

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Automatic license plate recognition requires a series of complex image processing steps. For practical use, the amount of data to he processed must be minimized early on. This paper shows that the computationally most intensive steps can be realized by DTCNNs. Moreover; high-level operations like finding the license plate in the image' and 'finding the characters on the plate' need only a smalt number of DTCNNs. Real-life tests show that the DTCNNs are capable of correctly identifying more than 85% out of all licence plates while leaving only 0.5% of the original information to be inspected for actual recognition.

引用

页码：212 / 217

页数：4